Fault Detection and Classification in Power Electronic Circuits Using Wavelet Transform and Neural Network | Science Publications

Journal of Computer Science

Nanjundappan Devarajan¹  Venugopal Prasannamoorthy¹ 

关键词: Fault diagnosis;    wavelet transform;    three phase inverter;    fault dictionary;    neural network classifier;    Circuit Under Test (CUT);    Standard Deviation (SD);    Fault Detection and Isolation (FDI);    Simulation-After-Test (SAT);    Simulation-Before-Test (SBT);   

DOI  :  10.3844/jcssp.2011.95.100

学科分类：计算机科学（综合）

来源: Science Publications

【 摘 要 】

Problem statement: The identification of faults in any analog circuit is highly required toensure the reliability of the circuit. Early detection of faults in a circuit can greatly assist inmaintenance of the system by avoiding possibly harmful damage borne out of the fault. Approach: Anovel method for establishing a fault dictionary using Wavelet transform is presented. The CircuitUnder Test (CUT) is three phase single level inverter. The transform coefficients for the fault freecircuit as well as for the simulated faults of CUT are found. The Wavelet transform is applied to theoutput of CUT and Standard Deviation (SD) of the transform coefficients are extracted. Using thetransform coefficients, fault dictionary has been formed. In order to identify the type of fault, a neuralnetwork classifier has been utilized. Results: The compatibility of wavelet analysis with the variousclassification techniques for fault diagnosis has been illustrated in this study. The results of the studydemonstrate the suitability and viability of wavelet analysis in fault diagnosis of power electroniccircuits. Conclusion: The proposed approach is found to be more reliable in accurate identification andisolation of faults using fault dictionary. Moreover, the neural classifier improves the efficiency of thesystem as neural networks do not require prior knowledge as they are capable of learning and evolvingthrough a number of learning algorithms.

【 授权许可】

Unknown